US 12,077,181 B1
Vehicle control using context-sensitive trajectory generation
Adrian Michael Costantino, Foster City, CA (US); Marin Kobilarov, Baltimore, MD (US); Mark Jonathon McClelland, San Francisco, CA (US); and Yunpeng Pan, Newark, CA (US)
Assigned to Zoox, Inc., Foster City, CA (US)
Filed by Zoox, Inc., Foster City, CA (US)
Filed on Sep. 30, 2021, as Appl. No. 17/491,483.
Int. Cl. B60W 60/00 (2020.01)
CPC B60W 60/0011 (2020.02) [B60W 2552/30 (2020.02); B60W 2720/10 (2013.01); B60W 2720/106 (2013.01); B60W 2720/12 (2013.01); B60W 2720/125 (2013.01); B60W 2720/24 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving sensor data associated with operation of a vehicle in an environment;
determining, based at least in part on the sensor data and a state of a set of states discretized based at least in part on one or more of a displacement along or a lateral distance from a route, a first candidate trajectory;
determining, based at least in part on at least one of the sensor data or map data, that a curvature associated with operating the vehicle in the environment meets or exceeds a threshold curvature;
altering a trajectory generation component based at least in part on determining that the curvature meets or exceeds a threshold curvature, wherein altering the trajectory generation component comprises determining, based at least in part on an arc length and the sensor data, a second candidate trajectory; and
controlling the vehicle based at least in part on the second candidate trajectory.